MCPcopy Create free account

hub / github.com/bronyayang/Law_of_Vision_Representation_in_MLLMs / functions

Functions12,826 in github.com/bronyayang/Law_of_Vision_Representation_in_MLLMs

⨍ Functions 12,826◇ Types & classes 1,844↳ Endpoints 18
↓ 2 callersMethod_threshold_sample
"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at t
diffusers/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py:298
↓ 2 callersMethod_threshold_sample
"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at t
diffusers/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py:411
↓ 2 callersMethod_threshold_sample
"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at t
diffusers/src/diffusers/schedulers/scheduling_ddpm_parallel.py:378
↓ 2 callersMethod_tiled_decode
r"""Encode a batch of images using a tiled encoder. When this option is enabled, the VAE will split the input tensor into tiles to compute en
diffusers/src/diffusers/models/autoencoders/autoencoder_tiny.py:246
↓ 2 callersMethod_tiled_encode
r"""Encode a batch of images using a tiled encoder. When this option is enabled, the VAE will split the input tensor into tiles to compute en
diffusers/src/diffusers/models/autoencoders/autoencoder_tiny.py:198
↓ 2 callersMethod_to_3d
(self, hidden_states: torch.Tensor, height: int, weight: int)
diffusers/src/diffusers/models/unets/unet_2d_blocks.py:3687
↓ 2 callersMethod_to_4d
(self, hidden_states: torch.Tensor, height: int, weight: int)
diffusers/src/diffusers/models/unets/unet_2d_blocks.py:3690
↓ 2 callersFunction_to_float
(text: str)
llava/eval/lmms-eval/lmms_eval/tasks/chartqa/utils.py:46
↓ 2 callersFunction_tokenize
(text)
llava/eval/lmms-eval/lmms_eval/tasks/websrc/utils.py:130
↓ 2 callersFunction_tokenize_fn
Tokenize a list of strings.
llava/train/train.py:304
↓ 2 callersFunction_tokenize_fn
Tokenize a list of strings.
llava/train/train_switch.py:241
↓ 2 callersFunction_translate_into_actual_layer_name
Translate user-friendly name (e.g. 'mid') into actual layer name (e.g. 'mid_block.attentions.0')
diffusers/src/diffusers/loaders/unet_loader_utils.py:27
↓ 2 callersMethod_update_latent
Update the latent according to the computed loss.
diffusers/src/diffusers/pipelines/stable_diffusion_attend_and_excite/pipeline_stable_diffusion_attend_and_excite.py:651
↓ 2 callersMethod_update_latent
Update the latent according to the computed loss.
diffusers/examples/community/pipeline_stable_diffusion_boxdiff.py:1168
↓ 2 callersMethod_upsample_2d
Fused `upsample_2d()` followed by `Conv2d()`. Padding is performed only once at the beginning, not between the operations. The fused op is co
diffusers/src/diffusers/models/upsampling.py:216
↓ 2 callersMethod_validate_config
(self)
llava/model/language_model/mpt/configuration_mpt.py:96
↓ 2 callersFunctionadd_noise
(original_samples: torch.Tensor, noise: torch.Tensor, timesteps: torch.Tensor)
diffusers/examples/research_projects/consistency_training/train_cm_ct_unconditional.py:147
↓ 2 callersMethodadd_noise
( self, original_samples: torch.Tensor, noise: torch.Tensor, timesteps: torch.
diffusers/src/diffusers/schedulers/scheduling_ddpm_wuerstchen.py:210
↓ 2 callersFunctionadd_order_label
(image, label, font_family="DejaVu Sans", font_size=40)
llava/eval/lmms-eval/lmms_eval/tasks/mmmu/utils_group_img.py:17
↓ 2 callersFunctionadd_special_tokens
(hidden_states, attention_mask, sos_token, eos_token)
diffusers/src/diffusers/pipelines/audioldm2/modeling_audioldm2.py:47
↓ 2 callersFunctionadd_tokens
Add tokens to the tokenizer and set the initial value of token embeddings
diffusers/examples/research_projects/multi_token_textual_inversion/textual_inversion.py:82
↓ 2 callersFunctionadd_transparency
Adds transparency to an image. :param image: PIL image object. :param transparency: Float representing the level of transparency (0.0 to
C_score/utils/utils_visualization.py:53
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_pndm.py:53
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_sasolver.py:56
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_lms_discrete.py:73
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_ddpm.py:73
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_dpmsolver_sde.py:104
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_repaint.py:72
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_k_dpm_2_ancestral_discrete.py:52
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_ddim_parallel.py:76
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_unclip.py:73
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_lcm.py:78
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_euler_ancestral_discrete.py:76
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_deis_multistep.py:55
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_ddpm_wuerstchen.py:69
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_k_dpm_2_discrete.py:51
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_consistency_decoder.py:39
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py:55
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_euler_discrete.py:76
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py:55
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_unipc_multistep.py:55
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_ddim.py:76
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_ddpm_parallel.py:75
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_ddim_inverse.py:74
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py:57
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_heun_discrete.py:51
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/src/diffusers/schedulers/scheduling_tcd.py:77
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/examples/community/latent_consistency_txt2img.py:347
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/examples/community/scheduling_ufogen.py:75
↓ 2 callersFunctionalpha_bar_fn
(t)
diffusers/examples/community/latent_consistency_img2img.py:432
↓ 2 callersFunctionappend_dims
Appends dimensions to the end of a tensor until it has target_dims dimensions.
diffusers/examples/consistency_distillation/train_lcm_distill_lora_sdxl.py:198
↓ 2 callersFunctionappend_dims
Appends dimensions to the end of a tensor until it has target_dims dimensions.
diffusers/examples/consistency_distillation/train_lcm_distill_lora_sd_wds.py:355
↓ 2 callersFunctionappend_dims
Appends dimensions to the end of a tensor until it has target_dims dimensions.
diffusers/examples/consistency_distillation/train_lcm_distill_sdxl_wds.py:321
↓ 2 callersFunctionappend_dims
Appends dimensions to the end of a tensor until it has target_dims dimensions.
diffusers/examples/consistency_distillation/train_lcm_distill_lora_sdxl_wds.py:342
↓ 2 callersFunctionappend_dims
Appends dimensions to the end of a tensor until it has target_dims dimensions.
diffusers/examples/consistency_distillation/train_lcm_distill_sd_wds.py:333
↓ 2 callersFunctionappend_dims
Appends dimensions to the end of a tensor until it has target_dims dimensions.
diffusers/examples/research_projects/consistency_training/train_cm_ct_unconditional.py:77
↓ 2 callersMethodapply
(self, resps, docs)
llava/eval/lmms-eval/lmms_eval/tasks/realworldqa/utils.py:70
↓ 2 callersFunctionapply_FRESCO_opt
Apply FRESCO-based optimization to a StableDiffusionPipeline
diffusers/examples/community/fresco_v2v.py:736
↓ 2 callersFunctionapply_rotary_emb
Apply rotary embeddings to input tensors using the given frequency tensor. This function applies rotary embeddings to the given query or key
diffusers/src/diffusers/models/embeddings.py:310
↓ 2 callersFunctionassign_correctness
(data_arr, correctness_entry)
llava/eval/lmms-eval/lmms_eval/tasks/hallusion_bench/utils.py:164
↓ 2 callersFunctionattention_from_original_checkpoint
(model, diffuser_attention_prefix, original_attention_prefix)
diffusers/scripts/convert_blipdiffusion_to_diffusers.py:86
↓ 2 callersFunctionauto_upgrade
(config)
llava/model/utils.py:4
↓ 2 callersFunctionbenchmark_fn
(f, *args, **kwargs)
diffusers/benchmarks/utils.py:52
↓ 2 callersFunctionbetas_for_alpha_bar
Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [
diffusers/src/diffusers/schedulers/scheduling_heun_discrete.py:26
↓ 2 callersMethodblend_h
(self, a: torch.Tensor, b: torch.Tensor, blend_extent: int)
diffusers/src/diffusers/models/autoencoders/autoencoder_kl.py:327
↓ 2 callersMethodblend_v
(self, a: torch.Tensor, b: torch.Tensor, blend_extent: int)
diffusers/src/diffusers/models/autoencoders/autoencoder_kl.py:321
↓ 2 callersFunctionblock_to_diffusers_checkpoint
(block, checkpoint, block_idx, block_type)
diffusers/scripts/convert_k_upscaler_to_diffusers.py:115
↓ 2 callersMethodbuild_choices
(self, item)
llava/eval/lmms-eval/lmms_eval/tasks/mmupd/mmupd_evals.py:145
↓ 2 callersMethodbuild_choices
(self, item)
llava/eval/lmms-eval/lmms_eval/tasks/mmbench/mmbench_evals.py:55
↓ 2 callersFunctionbuild_demo_classes_and_metadata
(vocab, label_list)
C_score/model_utils/extractor_sd.py:113
↓ 2 callersFunctionbytes_to_giga_bytes
(bytes)
diffusers/benchmarks/utils.py:48
↓ 2 callersFunctioncal_clip_loss
(image_features, text_features, logit_scale, self_logit_scale = None)
C_score/utils/utils_losses.py:78
↓ 2 callersFunctioncalc_mean_std
(feat, eps=1e-5, chunk=1)
diffusers/examples/community/fresco_v2v.py:153
↓ 2 callersMethodcalculate_hit_rates
(self, data)
llava/eval/lmms-eval/lmms_eval/tasks/mmupd/mmupd_evals.py:505
↓ 2 callersFunctioncalculate_ins_level_acc
(results)
llava/eval/lmms-eval/lmms_eval/tasks/cmmmu/utils.py:413
↓ 2 callersFunctioncalculate_ins_level_acc
Calculate the instruction level accuracy for given Subject results https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445782686b4c35
llava/eval/lmms-eval/lmms_eval/tasks/mmmu/utils.py:137
↓ 2 callersFunctioncalculate_ins_level_acc
Calculate the instruction level accuracy for given Subject results https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445782686b4c35
llava/eval/lmms-eval/lmms_eval/tasks/mmmu/utils_group_img.py:257
↓ 2 callersMethodcan_compute_power
(self, expr)
llava/eval/lmms-eval/lmms_eval/tasks/olympiadbench/olympiadbench_evals.py:342
↓ 2 callersMethodcheck_controlnet_conditioning_image
(self, image, prompt, prompt_embeds)
diffusers/examples/community/stable_diffusion_controlnet_inpaint.py:456
↓ 2 callersMethodcheck_controlnet_conditioning_image
(self, image, prompt, prompt_embeds)
diffusers/examples/community/stable_diffusion_controlnet_img2img.py:357
↓ 2 callersMethodcheck_image
(self, image, prompt, prompt_embeds)
diffusers/src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl.py:815
↓ 2 callersMethodcheck_image
(self, image, prompt, prompt_embeds)
diffusers/src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint_sd_xl.py:603
↓ 2 callersMethodcheck_image
(self, image, prompt, prompt_embeds)
diffusers/src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py:766
↓ 2 callersMethodcheck_image
(self, image, prompt, prompt_embeds)
diffusers/src/diffusers/pipelines/controlnet/pipeline_controlnet_img2img.py:731
↓ 2 callersMethodcheck_image
(self, image, prompt, prompt_embeds)
diffusers/src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl_img2img.py:821
↓ 2 callersMethodcheck_image
(self, image, prompt, prompt_embeds)
diffusers/examples/community/fresco_v2v.py:1877
↓ 2 callersMethodcheck_image
(self, image, prompt, prompt_embeds)
diffusers/examples/community/run_onnx_controlnet.py:378
↓ 2 callersMethodcheck_image
(self, image, prompt, prompt_embeds)
diffusers/examples/community/run_tensorrt_controlnet.py:482
↓ 2 callersMethodcheck_inputs
( self, prompt, height, width, callback_steps, negative_prompt
diffusers/examples/community/stable_diffusion_ipex.py:488
↓ 2 callersMethodcheck_inputs
( self, prompt, prompt_2, height, width, callback_steps,
diffusers/examples/community/pipeline_stable_diffusion_xl_ipex.py:536
↓ 2 callersMethodcheck_over_configs
(self, time_step=0, **config)
diffusers/tests/schedulers/test_scheduler_score_sde_ve.py:59
↓ 2 callersMethodcheck_over_forward
(self, time_step=0, **forward_kwargs)
diffusers/tests/schedulers/test_scheduler_pndm.py:59
↓ 2 callersMethodcheck_over_forward
(self, time_step=0, **forward_kwargs)
diffusers/tests/schedulers/test_scheduler_flax.py:732
↓ 2 callersFunctioncheck_valid_inputs
(*tensors, valid_dtypes=[torch.float16, torch.bfloat16])
llava/model/language_model/mpt/attention.py:64
↓ 2 callersMethodclassify_height_width_bin
Returns binned height and width.
diffusers/src/diffusers/image_processor.py:1074
↓ 2 callersFunctionclean_code
Remove docstrings, empty line or comments from some code (used to detect if a diff is real or only concern comments or docstings). Args:
diffusers/utils/tests_fetcher.py:106
↓ 2 callersMethodcleanup
(self, return_onnx=False)
diffusers/scripts/convert_stable_diffusion_controlnet_to_onnx.py:37
↓ 2 callersFunctioncoerce_attn_resolutions
(attn_resolutions)
diffusers/scripts/convert_vq_diffusion_to_diffusers.py:146
↓ 2 callersFunctioncoerce_resolution
(resolution)
diffusers/scripts/convert_vq_diffusion_to_diffusers.py:157
↓ 2 callersMethodcomplete_mask
Based on the input mask corresponding value `0 or 1` for each phrases and image, mask the features corresponding to phrases and image
diffusers/src/diffusers/pipelines/stable_diffusion_gligen/pipeline_stable_diffusion_gligen_text_image.py:562
← previousnext →1,301–1,400 of 12,826, ranked by callers